import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import plotly.express as px
import seaborn as sns
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn import metrics
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
import warnings
warnings.filterwarnings('ignore')

from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler


plt.style.use('ggplot')

# show all columns
pd.set_option('display.max_columns', 50)

train_data = pd.read_csv('phone_train.csv')
test_data = pd.read_csv('phone_test.csv')

df_train = pd.DataFrame(train_data)
df_test = pd.DataFrame(test_data)

df_train

df_test

df_train.describe()

df_test.describe()

m = df_train.isnull().sum()
if m.all() == 0:
    print('Missing values *train dataset*  =>>> False')
else:
    print('We have missing values in train dataset:\n', m)

Missing values *train dataset*  =>>> False

m = df_test.isnull().sum()
if m.all() == 0:
    print('Missing values *test dataset* =>>> False')
else:
    print('We have missing values in test dataset:\n', m)

Missing values *test dataset* =>>> False

df_train.hist(bins=100,figsize=(30,20))
plt.show()

plt.figure(figsize=(15, 10))
sns.heatmap(df_train.corr(numeric_only=[True]), cmap='Reds', cbar=True, annot=True, linewidths=0.5, annot_kws={"size": 8})
plt.title('Correlation Heatmap')
plt.xticks()
plt.xlabel('Features')
plt.ylabel('Features')
plt.show()

plt.figure(figsize=(15,5)) 
plt.scatter(x=df_train['ram'], y=df_train['price_range'])
plt.title('compare ram vs target',
            backgroundcolor='black',color='red',fontsize=15)
plt.xlabel('ram', fontsize = 15)
plt.ylabel('Price range', fontsize=15)

Text(0, 0.5, 'Price range')

fig = px.scatter(df_train, x='ram', y='price_range',
                  color='price_range', marginal_y='violin', marginal_x='box')

fig.update_layout(
    title='Compare RAM vs Price Range',
    title_x=0.5
)

fig.show()

sns.jointplot(x='ram', y='price_range', data=df_train, color='red', kind='kde')

<seaborn.axisgrid.JointGrid at 0x1f2f0997590>

fig = px.density_contour(df_train, x='ram', y='price_range')

fig.update_layout(
    title='Compare RAM vs Price Range',
    title_x=0.5,
    title_yanchor='top'
)

fig.show()

labels = ['3G-Supported', 'Not Supported']
values = df_train['three_g'].value_counts().values

fig = px.pie(values=values, 
              names=labels,
              hole=.3
            )
fig.update_layout(
    title_text="3G",
    title_x=0.45, 
    title_yanchor="middle"
)

fig.show()

labels = ['4G-Supported', 'Not Supported']
values = df_train['four_g'].value_counts().values

fig = px.pie(values=values,  
             names=labels,
             hole=.3
            )

fig.update_layout(
    title_text="4G",
    title_x=0.45, 
    title_yanchor="middle"
)

fig.show()

labels = ['1', '2', '3', '4', '5', '6', '7', '8']
values = df_train['n_cores'].value_counts().values

fig = px.pie(values=values,  
             names=labels,
             hole=0.3
            )

fig.update_layout(
    title_text="n_cores",
    title_x=0.5, 
    title_yanchor="middle"
)

fig.show()

df_train.describe()

fig = px.scatter(df_train, x='px_height', y='price_range', color='price_range', marginal_y='violin', marginal_x='box')

fig.update_layout(
    title='px_height vs Price Range (before)',
    title_x=0.5
)

fig.show()

df_train.px_height.describe()

count    2000.000000
mean      645.108000
std       443.780811
min         0.000000
25%       282.750000
50%       564.000000
75%       947.250000
max      1960.000000
Name: px_height, dtype: float64

print(df_train.px_height.min())

0

# Remove px_hight = 0
df_train = df_train[df_train['px_height']!=0]
df_train.reset_index(inplace=True)
df_train.drop('index', axis=1, inplace=True)

fig = px.scatter(df_train, x='px_height', y='price_range', color='price_range', marginal_y='violin', marginal_x='box')

fig.update_layout(
    title='px_height vs Price Range(after)',
    title_x=0.5
)

fig.show()

fig = px.scatter(df_train, x='sc_w', y='price_range', color='price_range', marginal_y='violin', marginal_x='box')

fig.update_layout(
    title='sc_w vs Price Range(before)',
    title_x=0.5
)

fig.show()

df_train.sc_w.describe()

count    1998.000000
mean        5.770270
std         4.356633
min         0.000000
25%         2.000000
50%         5.000000
75%         9.000000
max        18.000000
Name: sc_w, dtype: float64

print(df_train.px_height.min())

1

# Remove sc_w =< 2
df_train = df_train[df_train['sc_w'] >= 2]
df_train.reset_index(inplace=True)
df_train.drop('index', axis=1, inplace=True)

fig = px.scatter(df_train, x='sc_w', y='price_range', color='price_range', marginal_y='violin', marginal_x='box')

fig.update_layout(
    title='sc_w vs Price Range(after)',
    title_x=0.5
)

fig.show()

df_train

df_test.px_height.describe()

count    1000.000000
mean      627.121000
std       432.929699
min         0.000000
25%       263.750000
50%       564.500000
75%       903.000000
max      1907.000000
Name: px_height, dtype: float64

print(df_test.px_height.min())

0

# Remove px_hight = 0
df_test = df_test[df_test['px_height']!=0]
df_test.reset_index(inplace=True)
df_test.drop('index', axis=1, inplace=True)

df_test.sc_w.describe()

count    998.000000
mean       5.315631
std        4.244245
min        0.000000
25%        2.000000
50%        5.000000
75%        8.000000
max       18.000000
Name: sc_w, dtype: float64

print(df_test.sc_w.min())

0

# Remove sc_w =< 2
df_test = df_test[df_test['sc_w'] >= 2]
df_test.reset_index(inplace=True)
df_test.drop('index', axis=1, inplace=True)

df_test

Xd = df_train.drop('price_range', axis=1)
yd = df_train.price_range.values.reshape(-1, 1)

def DT(Xd, yd, test_sizes, max_depths, criterion, splitter):
    df_evaluation = pd.DataFrame(columns=['Test_size', 'Max_depth', 'Criterion', 'Splitter', 'Accuracy', 'Score'])
    for test_size in test_sizes:
        X_train, X_test, y_train, y_test = train_test_split(Xd, yd, test_size=test_size, random_state=0)
        for max_depth in max_depths:
            for c in criterion:
                for s in splitter:
                    clf = DecisionTreeClassifier(max_depth=max_depth, criterion=c, splitter=s)
                    clf.fit(X_train, y_train)
                    y_pred = clf.predict(X_test)
                    accuracy = metrics.accuracy_score(y_test, y_pred)
                    score = clf.score(Xd, yd)
                    df_evaluation = pd.concat([df_evaluation, pd.DataFrame({'Test_size': test_size,
                                                                            'Max_depth': max_depth,
                                                                            'Criterion': c,
                                                                            'Splitter': s,
                                                                            'Accuracy': accuracy,
                                                                            'Score': score}, index=[0])], ignore_index=True)


    return (df_evaluation)

def highlight_max(s):
    is_max = s == s.max()
    return ['background-color: lightgreen' if v else '' for v in is_max]

test_sizes = [0.1, 0.15, 0.2, 0.25, 0.3]
max_depths = list(range(1, 21))
criterion = ['gini', 'entropy', 'log_loss']
splitter = ['best', 'random']

df_evaluation = DT(Xd, yd, test_sizes, max_depths, criterion=criterion, splitter=splitter)
df_evaluation.style.apply(highlight_max)

X_train, X_test, y_train, y_test = train_test_split(Xd, yd, test_size=0.1, random_state=0)

clf_dts = DecisionTreeClassifier(max_depth=11, criterion='gini', splitter='best')
clf_dts.fit(X_train, y_train)
y_pred = clf_dts.predict(X_test)

print('Accuracy = ', metrics.accuracy_score(y_test, y_pred), '\nScore = ', clf_dts.score(Xd, yd))

Accuracy =  0.8757763975155279 
Score =  0.9863269111249223

Xr = df_train.drop('price_range', axis=1)
yr = df_train.price_range.values.reshape(-1, 1)

def RF(Xr, yr, Testsize, mdepth):
    df_evaluation = pd.DataFrame()
    for x in Testsize:
        X_train, X_test, y_train, y_test = train_test_split(Xr, yr, test_size=x, random_state=0)
        for maxdepth in mdepth:
            for n_estimators in [10, 50, 100, 200, 300]:
                for criterion in ["gini", "entropy", "log_loss"]:
                        RF = RandomForestClassifier(n_estimators=n_estimators,
                                                     criterion=criterion,
                                                     max_depth=maxdepth)
                        RF.fit(X_train, y_train)
                        y_pred = RF.predict(X_test)
                        dict = {'Test_size': x,
                                "Max_depth": maxdepth,
                                "n_estimators": n_estimators,
                                "criterion": criterion,
                                'acc': metrics.accuracy_score(y_test,y_pred),
                                "score": RF.score(Xr, yr)}
                        df_evaluation = pd.concat([df_evaluation, pd.DataFrame(dict, index=[0])], ignore_index=True)
    return(df_evaluation)


df_evaluation = RF(Xr, yr, [.1,.15,.2,.25,.3], range(1,21))
df_evaluation.style.apply(highlight_max)

X_train, X_test, y_train, y_test = train_test_split(Xr, yr, test_size=0.1, random_state=0)

clf_rf = RandomForestClassifier(max_depth=19, n_estimators=200, criterion='gini')
clf_rf.fit(X_train, y_train)
y_pred = clf_rf.predict(X_test)

print('Accuracy = ', metrics.accuracy_score(y_test, y_pred), '\nScore = ', clf_rf.score(Xr, yr))

Accuracy =  0.906832298136646 
Score =  0.9906774394033562

Xs = df_train.drop('price_range', axis=1)
ys = df_train.price_range.values.reshape(-1, 1)

def svc(Xs, ys, Testsize):
    df_evaluation_svm = pd.DataFrame()

    C_values = [0.1, 1, 10]
    kernel_values = ['linear', 'rbf', 'poly', 'sigmoid']
    decision_function_shape_values = ['ovo', 'ovr']
    degree_values = [2, 3, 4]
    gamma_values = ['scale', 'auto']

    for C in C_values:
        for kernel in kernel_values:
            for decision_function_shape in decision_function_shape_values:
                for degree in degree_values:
                    for gamma in gamma_values:
                        for x in Testsize:
                            X_train, X_test, y_train, y_test = train_test_split(Xs, ys, test_size=x, random_state=0)
                            svm = SVC(C=C, kernel=kernel, decision_function_shape=decision_function_shape, degree=degree, gamma=gamma)
                            svm.fit(X_train, y_train)
                            y_pred = svm.predict(X_test)
                            dict = {'C': C, 'kernel': kernel, 'decision_function_shape': decision_function_shape, 'degree': degree, 'gamma': gamma, 'Test_size': x, 'acc': metrics.accuracy_score(y_test, y_pred), 'score': svm.score(Xs, ys)}
                            df_evaluation_svm = pd.concat([df_evaluation_svm, pd.DataFrame(dict, index=[0])], ignore_index=True)

    return (df_evaluation_svm)


df_evaluation_svm = svc(Xs, ys, [.1, .15, .2, .25, .3])
df_evaluation_svm.style.apply(highlight_max)

X_train, X_test, y_train, y_test = train_test_split(Xs, ys, test_size=0.15, random_state=0)

clf_svm = SVC(C=0.1, kernel='linear', decision_function_shape='ovo',degree=2, gamma='scale')
clf_svm.fit(X_train, y_train)
y_pred = clf_svm.predict(X_test)

print('Accuracy = ', metrics.accuracy_score(y_test, y_pred), '\nScore = ', clf_svm.score(Xs, ys))

Accuracy =  0.9834710743801653 
Score =  0.9888129272840274

df_test

df_test = df_test.drop('id', axis=1)

predict = clf_svm.predict(df_test)

predict

array([3, 2, 1, 3, 3, 1, 3, 3, 3, 0, 2, 0, 2, 1, 3, 3, 1, 3, 0, 2, 0, 3,
       0, 2, 0, 3, 0, 0, 1, 3, 1, 1, 1, 2, 0, 0, 1, 3, 1, 1, 0, 0, 3, 1,
       3, 1, 3, 3, 1, 2, 1, 2, 1, 2, 2, 3, 0, 0, 2, 0, 3, 3, 0, 3, 0, 3,
       1, 3, 1, 2, 2, 1, 2, 2, 0, 0, 3, 0, 2, 0, 1, 2, 3, 3, 2, 3, 3, 3,
       2, 3, 0, 0, 3, 2, 1, 2, 0, 2, 3, 2, 2, 1, 1, 3, 1, 1, 1, 1, 2, 3,
       3, 2, 3, 2, 3, 2, 3, 3, 3, 3, 2, 2, 3, 3, 3, 1, 3, 0, 2, 0, 1, 0,
       0, 1, 2, 1, 0, 0, 1, 2, 2, 1, 0, 0, 1, 0, 1, 0, 2, 3, 3, 2, 3, 2,
       3, 2, 1, 1, 0, 1, 2, 0, 2, 3, 0, 2, 0, 3, 2, 3, 0, 1, 0, 3, 0, 0,
       2, 2, 1, 3, 3, 0, 3, 1, 2, 0, 0, 1, 3, 3, 3, 0, 0, 2, 3, 1, 3, 1,
       3, 1, 2, 3, 3, 1, 0, 1, 3, 1, 1, 3, 2, 1, 0, 1, 2, 1, 0, 3, 2, 3,
       3, 2, 3, 3, 2, 1, 1, 0, 2, 0, 0, 3, 0, 3, 0, 1, 2, 0, 2, 3, 1, 2,
       2, 1, 0, 0, 1, 3, 2, 0, 0, 0, 3, 0, 2, 3, 1, 2, 2, 2, 1, 3, 3, 2,
       2, 3, 3, 3, 3, 3, 1, 2, 3, 0, 1, 0, 3, 1, 2, 3, 0, 0, 0, 0, 2, 0,
       2, 2, 2, 2, 0, 0, 0, 3, 0, 3, 2, 2, 1, 2, 3, 1, 1, 2, 0, 1, 0, 3,
       2, 0, 0, 0, 0, 1, 1, 0, 0, 2, 2, 3, 2, 3, 0, 3, 0, 1, 0, 2, 0, 3,
       2, 3, 3, 1, 3, 1, 3, 3, 2, 0, 1, 2, 1, 0, 0, 1, 2, 1, 0, 3, 2, 0,
       2, 2, 0, 0, 3, 1, 0, 2, 3, 3, 0, 3, 2, 3, 2, 3, 0, 2, 0, 2, 0, 1,
       0, 1, 1, 1, 3, 3, 3, 2, 1, 2, 2, 3, 3, 3, 2, 2, 1, 2, 2, 1, 0, 2,
       2, 0, 0, 0, 3, 1, 0, 2, 2, 2, 0, 3, 2, 2, 1, 0, 3, 0, 1, 3, 1, 1,
       2, 2, 0, 2, 1, 2, 3, 1, 2, 2, 3, 2, 3, 1, 3, 2, 1, 1, 0, 0, 3, 1,
       0, 3, 3, 2, 1, 3, 3, 2, 3, 3, 2, 0, 1, 1, 2, 2, 2, 0, 0, 2, 2, 2,
       2, 1, 3, 3, 0, 1, 3, 2, 1, 1, 0, 0, 2, 1, 0, 1, 2, 0, 2, 2, 1, 0,
       3, 0, 0, 3, 0, 0, 1, 0, 0, 3, 0, 3, 1, 3, 2, 1, 3, 0, 1, 1, 3, 2,
       2, 0, 3, 0, 2, 0, 0, 1, 1, 2, 1, 1, 3, 2, 1, 3, 0, 2, 2, 3, 3, 0,
       2, 1, 2, 0, 3, 0, 3, 3, 3, 0, 2, 2, 3, 2, 2, 1, 2, 3, 0, 1, 0, 1,
       2, 0, 1, 0, 0, 3, 0, 2, 0, 1, 1, 0, 3, 2, 0, 0, 1, 2, 2, 1, 0, 1,
       2, 0, 1, 1, 0, 0, 3, 0, 3, 1, 3, 0, 1, 0, 2, 1, 0, 1, 1, 3, 2, 0,
       3, 2, 0, 0, 0, 3, 3, 2, 0, 2, 1, 3, 0, 2, 0, 3, 1, 2, 1, 1, 3, 1,
       1, 2, 1, 0, 2, 2, 0, 2, 0, 0, 0, 0, 2, 3, 0, 1, 1, 0, 1, 0, 2, 0,
       3, 2, 2, 1, 2, 0, 3, 3, 2, 3, 0, 2, 3, 3, 3, 2, 1, 0, 0, 3, 3, 1,
       0, 0, 0, 2, 2, 3, 2, 1, 2, 3, 3, 0, 1, 2, 1, 2, 2, 3, 1, 3, 0, 2,
       3, 2, 1, 1, 1, 3, 0, 2, 2, 3, 2, 2, 3, 2, 0, 1, 2, 1, 2, 2, 2, 1,
       2, 1, 1, 3, 1, 0, 1, 2, 1, 0, 3, 2, 3, 0, 3, 2, 1, 3, 0, 3, 1, 1,
       1, 3, 2, 0, 3, 0, 3, 0, 3, 3, 1, 0, 2, 3, 1, 0, 2, 2, 1, 2, 0, 2,
       2, 0, 2, 2, 3, 0, 2, 1, 1, 2, 2, 3, 3, 0, 2, 1, 2, 3, 1, 1, 3, 0,
       1, 0, 0, 3, 3, 2, 0, 0, 0, 3, 3, 3, 0, 0, 2, 2, 2], dtype=int64)

df_test['price_range'] = predict

df_test

labels = ['0', '1', '2', '3']
values = df_test['price_range'].value_counts().values

fig = px.pie(values=values,  
             names=labels,
             hole=0.3)

fig.update_layout(
    title_text="Price range of test dataset",
    title_x=0.5, 
    title_yanchor="middle"
)

fig.show()

	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	pc	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi	price_range
0	842	0	2.2	0	1	0	7	0.6	188	2	2	20	756	2549	9	7	19	0	0	1	1
1	1021	1	0.5	1	0	1	53	0.7	136	3	6	905	1988	2631	17	3	7	1	1	0	2
2	563	1	0.5	1	2	1	41	0.9	145	5	6	1263	1716	2603	11	2	9	1	1	0	2
3	615	1	2.5	0	0	0	10	0.8	131	6	9	1216	1786	2769	16	8	11	1	0	0	2
4	1821	1	1.2	0	13	1	44	0.6	141	2	14	1208	1212	1411	8	2	15	1	1	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1995	794	1	0.5	1	0	1	2	0.8	106	6	14	1222	1890	668	13	4	19	1	1	0	0
1996	1965	1	2.6	1	0	0	39	0.2	187	4	3	915	1965	2032	11	10	16	1	1	1	2
1997	1911	0	0.9	1	1	1	36	0.7	108	8	3	868	1632	3057	9	1	5	1	1	0	3
1998	1512	0	0.9	0	4	1	46	0.1	145	5	5	336	670	869	18	10	19	1	1	1	0
1999	510	1	2.0	1	5	1	45	0.9	168	6	16	483	754	3919	19	4	2	1	1	1	3

	id	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	pc	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi
0	1	1043	1	1.8	1	14	0	5	0.1	193	3	16	226	1412	3476	12	7	2	0	1	0
1	2	841	1	0.5	1	4	1	61	0.8	191	5	12	746	857	3895	6	0	7	1	0	0
2	3	1807	1	2.8	0	1	0	27	0.9	186	3	4	1270	1366	2396	17	10	10	0	1	1
3	4	1546	0	0.5	1	18	1	25	0.5	96	8	20	295	1752	3893	10	0	7	1	1	0
4	5	1434	0	1.4	0	11	1	49	0.5	108	6	18	749	810	1773	15	8	7	1	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
995	996	1700	1	1.9	0	0	1	54	0.5	170	7	17	644	913	2121	14	8	15	1	1	0
996	997	609	0	1.8	1	0	0	13	0.9	186	4	2	1152	1632	1933	8	1	19	0	1	1
997	998	1185	0	1.4	0	1	1	8	0.5	80	1	12	477	825	1223	5	0	14	1	0	0
998	999	1533	1	0.5	1	0	0	50	0.4	171	2	12	38	832	2509	15	11	6	0	1	0
999	1000	1270	1	0.5	0	4	1	35	0.1	140	6	19	457	608	2828	9	2	3	1	0	1

	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	pc	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi	price_range
count	2000.000000	2000.0000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000
mean	1238.518500	0.4950	1.522250	0.509500	4.309500	0.521500	32.046500	0.501750	140.249000	4.520500	9.916500	645.108000	1251.515500	2124.213000	12.306500	5.767000	11.011000	0.761500	0.503000	0.507000	1.500000
std	439.418206	0.5001	0.816004	0.500035	4.341444	0.499662	18.145715	0.288416	35.399655	2.287837	6.064315	443.780811	432.199447	1084.732044	4.213245	4.356398	5.463955	0.426273	0.500116	0.500076	1.118314
min	501.000000	0.0000	0.500000	0.000000	0.000000	0.000000	2.000000	0.100000	80.000000	1.000000	0.000000	0.000000	500.000000	256.000000	5.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000
25%	851.750000	0.0000	0.700000	0.000000	1.000000	0.000000	16.000000	0.200000	109.000000	3.000000	5.000000	282.750000	874.750000	1207.500000	9.000000	2.000000	6.000000	1.000000	0.000000	0.000000	0.750000
50%	1226.000000	0.0000	1.500000	1.000000	3.000000	1.000000	32.000000	0.500000	141.000000	4.000000	10.000000	564.000000	1247.000000	2146.500000	12.000000	5.000000	11.000000	1.000000	1.000000	1.000000	1.500000
75%	1615.250000	1.0000	2.200000	1.000000	7.000000	1.000000	48.000000	0.800000	170.000000	7.000000	15.000000	947.250000	1633.000000	3064.500000	16.000000	9.000000	16.000000	1.000000	1.000000	1.000000	2.250000
max	1998.000000	1.0000	3.000000	1.000000	19.000000	1.000000	64.000000	1.000000	200.000000	8.000000	20.000000	1960.000000	1998.000000	3998.000000	19.000000	18.000000	20.000000	1.000000	1.000000	1.000000	3.000000

	id	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	pc	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi
count	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.00000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.00000	1000.000000
mean	500.500000	1248.510000	0.516000	1.540900	0.517000	4.593000	0.487000	33.652000	0.517500	139.51100	4.328000	10.054000	627.121000	1239.774000	2138.998000	11.995000	5.316000	11.085000	0.756000	0.50000	0.507000
std	288.819436	432.458227	0.499994	0.829268	0.499961	4.463325	0.500081	18.128694	0.280861	34.85155	2.288155	6.095099	432.929699	439.670981	1088.092278	4.320607	4.240062	5.497636	0.429708	0.50025	0.500201
min	1.000000	500.000000	0.000000	0.500000	0.000000	0.000000	0.000000	2.000000	0.100000	80.00000	1.000000	0.000000	0.000000	501.000000	263.000000	5.000000	0.000000	2.000000	0.000000	0.00000	0.000000
25%	250.750000	895.000000	0.000000	0.700000	0.000000	1.000000	0.000000	18.000000	0.300000	109.75000	2.000000	5.000000	263.750000	831.750000	1237.250000	8.000000	2.000000	6.750000	1.000000	0.00000	0.000000
50%	500.500000	1246.500000	1.000000	1.500000	1.000000	3.000000	0.000000	34.500000	0.500000	139.00000	4.000000	10.000000	564.500000	1250.000000	2153.500000	12.000000	5.000000	11.000000	1.000000	0.50000	1.000000
75%	750.250000	1629.250000	1.000000	2.300000	1.000000	7.000000	1.000000	49.000000	0.800000	170.00000	6.000000	16.000000	903.000000	1637.750000	3065.500000	16.000000	8.000000	16.000000	1.000000	1.00000	1.000000
max	1000.000000	1999.000000	1.000000	3.000000	1.000000	19.000000	1.000000	64.000000	1.000000	200.00000	8.000000	20.000000	1907.000000	1998.000000	3989.000000	19.000000	18.000000	20.000000	1.000000	1.00000	1.000000

	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	pc	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi	price_range
count	2000.000000	2000.0000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000
mean	1238.518500	0.4950	1.522250	0.509500	4.309500	0.521500	32.046500	0.501750	140.249000	4.520500	9.916500	645.108000	1251.515500	2124.213000	12.306500	5.767000	11.011000	0.761500	0.503000	0.507000	1.500000
std	439.418206	0.5001	0.816004	0.500035	4.341444	0.499662	18.145715	0.288416	35.399655	2.287837	6.064315	443.780811	432.199447	1084.732044	4.213245	4.356398	5.463955	0.426273	0.500116	0.500076	1.118314
min	501.000000	0.0000	0.500000	0.000000	0.000000	0.000000	2.000000	0.100000	80.000000	1.000000	0.000000	0.000000	500.000000	256.000000	5.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000
25%	851.750000	0.0000	0.700000	0.000000	1.000000	0.000000	16.000000	0.200000	109.000000	3.000000	5.000000	282.750000	874.750000	1207.500000	9.000000	2.000000	6.000000	1.000000	0.000000	0.000000	0.750000
50%	1226.000000	0.0000	1.500000	1.000000	3.000000	1.000000	32.000000	0.500000	141.000000	4.000000	10.000000	564.000000	1247.000000	2146.500000	12.000000	5.000000	11.000000	1.000000	1.000000	1.000000	1.500000
75%	1615.250000	1.0000	2.200000	1.000000	7.000000	1.000000	48.000000	0.800000	170.000000	7.000000	15.000000	947.250000	1633.000000	3064.500000	16.000000	9.000000	16.000000	1.000000	1.000000	1.000000	2.250000
max	1998.000000	1.0000	3.000000	1.000000	19.000000	1.000000	64.000000	1.000000	200.000000	8.000000	20.000000	1960.000000	1998.000000	3998.000000	19.000000	18.000000	20.000000	1.000000	1.000000	1.000000	3.000000

Mobile Price Project Using Classification Algorithms ( Decission Trees, Random Forest, SVM )¶

Import libraries¶

Import Datasets¶

Preprocesing¶

px_height¶

sc_w¶

px_height¶

sc_w¶

Model¶

DecisionTrees¶

RandomForest¶

SVM¶

Best model =>SVM¶

Predict Test data¶

	Test_size	Max_depth	Criterion	Splitter	Accuracy	Score
0	0.100000	1	gini	best	0.521739	0.497203
1	0.100000	1	gini	random	0.409938	0.442511
2	0.100000	1	entropy	best	0.521739	0.497203
3	0.100000	1	entropy	random	0.434783	0.461778
4	0.100000	1	log_loss	best	0.521739	0.497203
5	0.100000	1	log_loss	random	0.521739	0.494096
6	0.100000	2	gini	best	0.776398	0.766314
7	0.100000	2	gini	random	0.509317	0.552517
8	0.100000	2	entropy	best	0.770186	0.766314
9	0.100000	2	entropy	random	0.565217	0.597887
10	0.100000	2	log_loss	best	0.770186	0.766314
11	0.100000	2	log_loss	random	0.472050	0.455562
12	0.100000	3	gini	best	0.788820	0.775637
13	0.100000	3	gini	random	0.559006	0.582349
14	0.100000	3	entropy	best	0.770186	0.766314
15	0.100000	3	entropy	random	0.745342	0.729646
16	0.100000	3	log_loss	best	0.770186	0.766314
17	0.100000	3	log_loss	random	0.782609	0.719702
18	0.100000	4	gini	best	0.838509	0.839030
19	0.100000	4	gini	random	0.782609	0.770044
20	0.100000	4	entropy	best	0.826087	0.817278
21	0.100000	4	entropy	random	0.757764	0.769422
22	0.100000	4	log_loss	best	0.826087	0.817278
23	0.100000	4	log_loss	random	0.757764	0.747048
24	0.100000	5	gini	best	0.813665	0.881914
25	0.100000	5	gini	random	0.763975	0.768800
26	0.100000	5	entropy	best	0.788820	0.874456
27	0.100000	5	entropy	random	0.782609	0.789932
28	0.100000	5	log_loss	best	0.788820	0.874456
29	0.100000	5	log_loss	random	0.770186	0.773151
30	0.100000	6	gini	best	0.826087	0.916097
31	0.100000	6	gini	random	0.627329	0.691112
32	0.100000	6	entropy	best	0.801242	0.907396
33	0.100000	6	entropy	random	0.813665	0.806091
34	0.100000	6	log_loss	best	0.801242	0.907396
35	0.100000	6	log_loss	random	0.801242	0.814792
36	0.100000	7	gini	best	0.819876	0.941579
37	0.100000	7	gini	random	0.813665	0.870106
38	0.100000	7	entropy	best	0.826087	0.945308
39	0.100000	7	entropy	random	0.726708	0.745183

	Test_size	Max_depth	n_estimators	criterion	acc	score
0	0.100000	1	10	gini	0.565217	0.533872
1	0.100000	1	10	entropy	0.527950	0.523306
2	0.100000	1	10	log_loss	0.527950	0.528278
3	0.100000	1	50	gini	0.621118	0.628341
4	0.100000	1	50	entropy	0.540373	0.563704
5	0.100000	1	50	log_loss	0.614907	0.576756
6	0.100000	1	100	gini	0.670807	0.679304
7	0.100000	1	100	entropy	0.596273	0.582971
8	0.100000	1	100	log_loss	0.590062	0.566812
9	0.100000	1	200	gini	0.677019	0.666252
10	0.100000	1	200	entropy	0.602484	0.587321
11	0.100000	1	200	log_loss	0.590062	0.589807
12	0.100000	1	300	gini	0.664596	0.696085
13	0.100000	1	300	entropy	0.608696	0.576756
14	0.100000	1	300	log_loss	0.621118	0.587321
15	0.100000	2	10	gini	0.658385	0.679925
16	0.100000	2	10	entropy	0.658385	0.663145
17	0.100000	2	10	log_loss	0.571429	0.575513
18	0.100000	2	50	gini	0.726708	0.791175
19	0.100000	2	50	entropy	0.801242	0.805469
20	0.100000	2	50	log_loss	0.720497	0.727781
21	0.100000	2	100	gini	0.739130	0.764450
22	0.100000	2	100	entropy	0.664596	0.690491
23	0.100000	2	100	log_loss	0.664596	0.717837
24	0.100000	2	200	gini	0.763975	0.795525
25	0.100000	2	200	entropy	0.726708	0.740211
26	0.100000	2	200	log_loss	0.708075	0.701057
27	0.100000	2	300	gini	0.782609	0.796147
28	0.100000	2	300	entropy	0.739130	0.712865
29	0.100000	2	300	log_loss	0.739130	0.753263
30	0.100000	3	10	gini	0.689441	0.755749
31	0.100000	3	10	entropy	0.596273	0.646364
32	0.100000	3	10	log_loss	0.695652	0.721566
33	0.100000	3	50	gini	0.813665	0.825979
34	0.100000	3	50	entropy	0.807453	0.812927
35	0.100000	3	50	log_loss	0.807453	0.829708
36	0.100000	3	100	gini	0.807453	0.837787
37	0.100000	3	100	entropy	0.813665	0.841516
38	0.100000	3	100	log_loss	0.745342	0.796147
39	0.100000	3	200	gini	0.788820	0.842138

	C	kernel	decision_function_shape	degree	gamma	Test_size	acc	score
0	0.100000	linear	ovo	2	scale	0.100000	0.981366	0.987570
1	0.100000	linear	ovo	2	scale	0.150000	0.983471	0.988813
2	0.100000	linear	ovo	2	scale	0.200000	0.965839	0.987570
3	0.100000	linear	ovo	2	scale	0.250000	0.965261	0.985705
4	0.100000	linear	ovo	2	scale	0.300000	0.964803	0.983841
5	0.100000	linear	ovo	2	auto	0.100000	0.981366	0.987570
6	0.100000	linear	ovo	2	auto	0.150000	0.983471	0.988813
7	0.100000	linear	ovo	2	auto	0.200000	0.965839	0.987570
8	0.100000	linear	ovo	2	auto	0.250000	0.965261	0.985705
9	0.100000	linear	ovo	2	auto	0.300000	0.964803	0.983841
10	0.100000	linear	ovo	3	scale	0.100000	0.981366	0.987570
11	0.100000	linear	ovo	3	scale	0.150000	0.983471	0.988813
12	0.100000	linear	ovo	3	scale	0.200000	0.965839	0.987570
13	0.100000	linear	ovo	3	scale	0.250000	0.965261	0.985705
14	0.100000	linear	ovo	3	scale	0.300000	0.964803	0.983841
15	0.100000	linear	ovo	3	auto	0.100000	0.981366	0.987570
16	0.100000	linear	ovo	3	auto	0.150000	0.983471	0.988813
17	0.100000	linear	ovo	3	auto	0.200000	0.965839	0.987570
18	0.100000	linear	ovo	3	auto	0.250000	0.965261	0.985705
19	0.100000	linear	ovo	3	auto	0.300000	0.964803	0.983841
20	0.100000	linear	ovo	4	scale	0.100000	0.981366	0.987570
21	0.100000	linear	ovo	4	scale	0.150000	0.983471	0.988813
22	0.100000	linear	ovo	4	scale	0.200000	0.965839	0.987570
23	0.100000	linear	ovo	4	scale	0.250000	0.965261	0.985705
24	0.100000	linear	ovo	4	scale	0.300000	0.964803	0.983841
25	0.100000	linear	ovo	4	auto	0.100000	0.981366	0.987570
26	0.100000	linear	ovo	4	auto	0.150000	0.983471	0.988813
27	0.100000	linear	ovo	4	auto	0.200000	0.965839	0.987570
28	0.100000	linear	ovo	4	auto	0.250000	0.965261	0.985705
29	0.100000	linear	ovo	4	auto	0.300000	0.964803	0.983841
30	0.100000	linear	ovr	2	scale	0.100000	0.981366	0.987570
31	0.100000	linear	ovr	2	scale	0.150000	0.983471	0.988813
32	0.100000	linear	ovr	2	scale	0.200000	0.965839	0.987570
33	0.100000	linear	ovr	2	scale	0.250000	0.965261	0.985705
34	0.100000	linear	ovr	2	scale	0.300000	0.964803	0.983841
35	0.100000	linear	ovr	2	auto	0.100000	0.981366	0.987570
36	0.100000	linear	ovr	2	auto	0.150000	0.983471	0.988813
37	0.100000	linear	ovr	2	auto	0.200000	0.965839	0.987570
38	0.100000	linear	ovr	2	auto	0.250000	0.965261	0.985705
39	0.100000	linear	ovr	2	auto	0.300000	0.964803	0.983841

Mobile Price Project Using Classification Algorithms ( Decission Trees, Random Forest, SVM )¶

Import libraries¶

Import Datasets¶

Preprocesing¶

px_height¶

sc_w¶

px_height¶

sc_w¶

Model¶

DecisionTrees¶

RandomForest¶

SVM¶

Best model =>SVM¶

Predict Test data¶

If you want to run this code again, you will not get my answer. This difference is related to the algorithms used.¶